Hengliang Tang
Papers
5
Total Citations
155
H-Index
4
About
Hengliang Tang is a leading researcher in intelligent warehouse automation and multi-robot systems, with a focus on task allocation, reinforcement learning, and edge computing. His work addresses critical challenges in dynamic logistics environments, particularly the efficient coordination of large-scale robot fleets in goods-to-man systems. Tang’s major contributions include developing a hierarchical Soft Actor-Critic algorithm that optimizes real-time task scheduling for AGV robots, and pioneering methods to transform multi-robot task allocation into solvable coalition-based problems. His research on hybrid many-objective competitive swarm optimization further advances large-scale multi-robot coordination. With over 150 total citations, his most cited paper (58 citations) on hierarchical reinforcement learning for logistics robots has significantly influenced the field. Tang also explores the integration of edge computing to reduce latency in cloud-robot task scheduling, and his work on multi-agent cooperation game theory provides foundational insights for hierarchical reinforcement learning. His innovative algorithms are widely applied in intelligent warehouse picking systems, improving efficiency and scalability. Tang’s research continues to shape the future of autonomous logistics and multi-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5